{"id":"https://openalex.org/W7148281569","doi":"https://doi.org/10.1109/asru65441.2025.11434618","title":"Analysing the Language of Neural Audio Codecs","display_name":"Analysing the Language of Neural Audio Codecs","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148281569","doi":"https://doi.org/10.1109/asru65441.2025.11434618"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109692719","display_name":"Joonyong Park","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Joonyong Park","raw_affiliation_strings":["The University of Tokyo"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinnosuke Takamichi","raw_affiliation_strings":["The University of Tokyo"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060692580","display_name":"D. Ching-Yao Chan","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David M. Chan","raw_affiliation_strings":["University of California,Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011471256","display_name":"Shunsuke Kando","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shunsuke Kando","raw_affiliation_strings":["The University of Tokyo"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132793760","display_name":"Yuki Saito","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Saito","raw_affiliation_strings":["The University of Tokyo"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132825754","display_name":"Hiroshi Saruwatari","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Saruwatari","raw_affiliation_strings":["The University of Tokyo"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5109692719"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87549262,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.2556999921798706,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.2556999921798706,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.10409999638795853,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10788","display_name":"Neuroscience and Music Perception","score":0.10119999945163727,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.616100013256073},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5594000220298767},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.48899999260902405},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4706000089645386},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4641999900341034},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.4627000093460083},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4465999901294708},{"id":"https://openalex.org/keywords/statistical-analysis","display_name":"Statistical analysis","score":0.37619999051094055}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7200999855995178},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.616100013256073},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6157000064849854},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5594000220298767},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.48899999260902405},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47929999232292175},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4641999900341034},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.4627000093460083},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4465999901294708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3862999975681305},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.37619999051094055},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.31290000677108765},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.2597000002861023},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.45427826046943665,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1605433909","https://openalex.org/W2000042664","https://openalex.org/W2079145130","https://openalex.org/W2166481425","https://openalex.org/W2593116425","https://openalex.org/W2963242190","https://openalex.org/W2972359262","https://openalex.org/W2972802841","https://openalex.org/W3209059054","https://openalex.org/W3215615641","https://openalex.org/W4205689591","https://openalex.org/W4225905067","https://openalex.org/W4225956675","https://openalex.org/W4281492411","https://openalex.org/W4372270198","https://openalex.org/W4375868953","https://openalex.org/W4381786045","https://openalex.org/W4392903389","https://openalex.org/W4392904232","https://openalex.org/W4402112643","https://openalex.org/W4402118927","https://openalex.org/W4417305271","https://openalex.org/W7133219565"],"related_works":[],"abstract_inverted_index":{"This":[0],"study":[1],"presents":[2],"a":[3],"comparative":[4],"analysis":[5],"of":[6,12,69,97,120,128],"the":[7,76,118,126],"statistical":[8,32,89],"and":[9,38,46,57,73,110,124],"linguistic":[10,31],"properties":[11,53],"neural":[13],"audio":[14],"codecs":[15],"(NACs).":[16],"We":[17],"investigate":[18],"discrete":[19],"speech":[20,71,108,132],"tokens":[21],"produced":[22],"by":[23],"various":[24],"NAC":[25,83,121],"models,":[26],"examining":[27],"their":[28,44],"adherence":[29],"to":[30,55,102],"laws":[33],"such":[34],"as":[35,41,43],"Zipf\u2019s":[36],"law":[37],"Heaps\u2019":[39],"law,":[40],"well":[42],"entropy":[45],"redundancy.":[47],"To":[48],"assess":[49],"how":[50],"these":[51,92],"token-level":[52],"relate":[54],"semantic":[56],"acoustic":[58],"preservation":[59],"in":[60,107],"synthesized":[61],"speech,":[62],"we":[63],"evaluate":[64],"intelligibility":[65],"using":[66,75],"error":[67],"rates":[68],"automatic":[70],"recognition,":[72],"quality":[74],"UTMOS":[77],"score.":[78],"Our":[79],"results":[80],"reveal":[81],"that":[82],"tokens,":[84],"particularly":[85],"3-grams,":[86],"exhibit":[87],"language-like":[88],"patterns.":[90],"Moreover,":[91],"properties,":[93],"together":[94],"with":[95,104],"measures":[96],"information":[98],"content,":[99],"are":[100],"found":[101],"correlate":[103],"improved":[105],"performances":[106],"recognition":[109],"resynthesis":[111],"tasks.":[112],"These":[113],"findings":[114],"offer":[115],"insights":[116],"into":[117],"structure":[119],"token":[122],"sequences":[123],"inform":[125],"design":[127],"more":[129],"effective":[130],"generative":[131],"models.":[133]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}